Model page

aufklarer/Qwen3-0.6B-Chat-CoreML warn

Weights only ship in a format that can run code when loaded; its architecture doesn't match its claimed base model.

downloads 17likes 0license apache-2.0arch qwen3_chatupdated 2026-05-28

claims base: Qwen/Qwen3-0.6B · chat template: present · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights batteryqueuedBehavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadqueued
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

Scanned 2026-08-25 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (Qwen3Chat-INT4.mlmodelc/analytics/coremldata.bin, Qwen3Chat-INT4.mlmodelc/coremldata.bin, Qwen3Chat-INT4.mlmodelc/weights/weight.bin, …). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.

How to fix

Convert the weights to safetensors before loading them anywhere that matters.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
  3. Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.

medium Architecture differs from claimed parent (qwen3_chat vs qwen3)

This model declares Qwen/Qwen3-0.6B as its base, but its config declares architecture 'qwen3_chat' while the parent is 'qwen3'. A finetune, merge, or quantization cannot change the architecture family — the lineage label is wrong or misleading, so treat provenance claims (training data, safety posture, licensing) as unverified.

How to fix

Fix or verify the `base_model` declaration so lineage checks can run.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-25.

architectureqwen3_chat
licenseapache-2.0
serializationno safetensors pickle
chat templatepresent (chat_template.jinja) · sha256:a55ee1b1660128b7
claimed lineageQwen/Qwen3-0.6B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
librarycoremltools
pipelinetext-generation
repo files27 — pickle: Qwen3Chat-INT4.mlmodelc/analytics/coremldata.bin, Qwen3Chat-INT4.mlmodelc/coremldata.bin, Qwen3Chat-INT4.mlmodelc/weights/weight.bin, Qwen3Chat-INT4.mlpackage/Data/com.apple.CoreML/weights/weight.bin, Qwen3Chat-INT8.mlmodelc/analytics/coremldata.bin, Qwen3Chat-INT8.mlmodelc/coremldata.bin, Qwen3Chat-INT8.mlmodelc/weights/weight.bin, Qwen3Chat-INT8.mlpackage/Data/com.apple.CoreML/weights/weight.bin
revisiona92923a0a362
HF snapshot17 downloads · 0 likes · updated 2026-05-28 · captured 2026-08-25
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightsqueued2026-08-25 22:190

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/aufklarer/Qwen3-0.6B-Chat-CoreML/badge.svg)](https://ingot.tools/models/aufklarer/Qwen3-0.6B-Chat-CoreML)
Gate it in CI